| ▲ | csours 3 days ago | |
You're absolutely right! Humans really like emotional validation. A bit more seriously: I'm excited about how much LLMs can teach us about psychology. I'm less excited about the dependency. --- Adding a bit more substantial comment: Users of sites like Stack Overflow have reported really disliking answers like "You are solving the wrong problem" or "This is a bad approach". There are different solutions possible, both for any technical problem, and for any meta-problem. Whatever garnish you put on top of the problem, the bitter lesson suggests that more data and more problem context improve the solution faster than whatever you are thinking right now. That's why it's called the bitter lesson. | ||
| ▲ | nullc 2 days ago | parent | next [-] | |
> Users of sites like Stack Overflow have reported really disliking answers like "You are solving the wrong problem" or "This is a bad approach". https://nt4tn.net/articles/aixy.html > Humans really like emotional validation. Personally, I find the sycophantic responses extremely ick and now generally won't use commercial LLMs at all due to it. Of course, I realize it's irrational to have any kind of emotional response to the completion bot's tone, but I just find it completely repulsive. In my case I already have a innate distaste for GPT 'house style' due to a abusive person who has harassed me for years adopting ChatGPT for all his communication, so any obviously 'chatgpt tone' comes across to me as that guy. But I think the revulsion at the sycophancy is unrelated. | ||
| ▲ | boogieknite 3 days ago | parent | prev [-] | |
most people commenting here have some sort of ick when it comes to fake praise. most poeple i know and work with seem to expect positive reinforcement and anything less risks coming off as rude or insulting ill speak for myself that im guilty of similar, less transparent, "customers always right" sycophancy dealing with client and management feature requests | ||